×

The Poisson random effect model for experience ratemaking: limitations and alternative solutions. (English) Zbl 1435.91157

Summary: Poisson random effect models with a shared random effect have been widely used in actuarial science for analyzing the number of claims. In particular, the random effect is a key factor in a posteriori risk classification. However, the necessity of the random effect may not be properly assessed due to the dual role of the random effect; it affects both the marginal distribution of the number of claims and the dependence among the numbers of claims obtained from an individual over time. We first show that the score test for the nullity of the variance of the shared random effect can falsely indicate significant dependence among the numbers of claims even though they are independent. To mitigate this problem, we propose to separate the dual role of the random effect by introducing additional random effects to capture the overdispersion part, which are called saturated random effects. In order to circumvent heavy computational issues by the saturated random effects, we choose a gamma distribution for the saturated random effects because it gives the closed form of marginal distribution. In fact, this choice leads to the negative binomial random effect model that has been widely used for the analysis of frequency data. We show that safer conclusions about the a posteriori risk classification can be made based on the negative binomial mixed model under various situations. We also derive the score test as a sufficient condition for the existence of the a posteriori risk classification based on the proposed model.

MSC:

91G05 Actuarial mathematics

Software:

bfa
PDFBibTeX XMLCite
Full Text: DOI arXiv

References:

[1] Antonio, K.; Valdez, E. A., Statistical concepts of a priori and a posteriori risk classification in insurance, AStA Adv. Stat. Anal., 96, 2, 187-224 (2012) · Zbl 1443.62328
[2] Booth, J. G.; Casella, G.; Friedl, H.; Hobert, J. P., Negative binomial loglinear mixed models, Stat. Model., 3, 3, 179-191 (2003) · Zbl 1070.62058
[3] Boucher, J.-P.; Denuit, M., Fixed versus random effects in Poisson regression models for claim counts: A case study with motor insurance, Astin Bull., 36, 01, 285-301 (2006) · Zbl 1162.91398
[4] Boucher, J.-P.; Denuit, M., Credibility premiums for the zero-inflated Poisson model and new hunger for bonus interpretation, Insurance Math. Econom., 42, 2, 727-735 (2008) · Zbl 1152.91567
[5] Boucher, J.-P.; Denuit, M.; Guillen, M., Models of insurance claim counts with time dependence based on generalization of Poisson and negative binomial distributions, Variance, 2, 1, 135-162 (2008)
[6] Boucher, J.; Inoussa, R., A posteriori ratemaking with panel data, Astin Bull., 2, 1, 587-612 (2014) · Zbl 1431.91319
[7] Bühlmann, H.; Gisler, A., A Course in Credibility Theory and its Applications (2006), Springer Science & Business Media
[8] Chesher, A., Testing for neglected heterogeneity, Econometrica, 52, 865-872 (1984) · Zbl 0564.62096
[9] De Jong, P.; Heller, G. Z., Generalized Linear Models for Insurance Data (2008), Cambridge University Press · Zbl 1142.91046
[10] Denuit, M.; Maréchal, X.; Pitrebois, S.; Walhin, J.-F., Actuarial Modelling of Claim Counts: Risk Classification, Credibility and Bonus-Malus Systems (2007), John Wiley & Sons · Zbl 1168.91001
[11] Frees, E. W., Regression Modeling with Actuarial and Financial Applications (2010), Cambridge University Press · Zbl 1284.62010
[12] Heagerty, P. J.; Kurland, B. F., Misspecified maximum likelihood estimates and generalised linear mixed models, Biometrika, 88, 4, 973-985 (2001) · Zbl 0986.62060
[13] Lawless, J. F., Negative binomial and mixed Poisson regression, Canad. J. Statist., 15, 3, 209-225 (1987) · Zbl 0632.62060
[14] Liang, K., A locally most powerful test for homogeneity with many strata, Biometrika, 74, 259-264 (1987) · Zbl 0621.62025
[15] McCulloch, C. E.; Neuhaus, J. M., Misspecifying the shape of a random effects distribution: why getting it wrong may not matter, Stat. Sci., 388-402 (2011) · Zbl 1246.62169
[16] Molenberghs, G.; Verbeke, G., Models for Discrete Longitudinal Data (2005), Springer · Zbl 1093.62002
[17] Murray, J. S.; Dunson, D. B.; Carin, L.; Lucas, J. E., Bayesian Gaussian copula factor models for mixed data, J. Amer. Statist. Assoc., 108, 502, 656-665 (2013) · Zbl 06195968
[18] Pinquet, J., Allowance for cost of claims in bonus-malus systems, Astin Bull., 27, 01, 33-57 (1997)
[19] Pinquet, J., Designing optimal bonus-malus systems from different types of claims, Astin Bull., 28, 02, 205-220 (1998) · Zbl 1162.91430
[20] Yang, Z.; Hardin, J.; Addy, C.; Vuong, Q., Testing approaches for overdispersion in Poisson regression versus the Generalized Poisson Model, Biom. J., 49, 4, 565-584 (2007) · Zbl 1442.62709
[21] Yip, K. C.; Yau, K. K., On modeling claim frequency data in general insurance with extra zeros, Insurance Math. Econom., 36, 2, 153-163 (2005) · Zbl 1070.62098
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.